Parallel algorithms for stereo vision shape from stereo
|
|
- Eugene Wright
- 6 years ago
- Views:
Transcription
1 Parallel algorithms for stereo vision shape from stereo XINGJIE RUAN, XENOPHON Institute of Information & Mathematical Sciences Massey University at Albany, Auckland, New Zealand
2 Parallel algorithms for stereo vision shape from stereo XINGJIE RUAN, XENOPHON Institute of Information & Mathematical Sciences Massey University at Albany, Auckland, New Zealand This paper proposes the parallel algorithms for stereo vision. The author present the concept of stereo vision, the existing stereo vision system in the world, the advantage of using parallel in stereo vision and the parallel algorithms for stereo vision Keywords: parallel; stereo vision; algorithms; correspondence. 1 Introduction Almost all the human beings got the stereo vision. People know objects are moving in the recognition of stereo vision. Parallel processing has been used in computer vision over the past two decades. And also, nowadays, stereo vision becomes an important part of computer vision. Stereo vision used in many areas of computer vision. For example, stereo vision can be used in robots, the robot can use their stereo vision to detect the distance between itself and the target object. Stereo vision can be used in the security system, to join two or more images together, so that can increase the range of vision. In the another hand, how to build stereo vision in real time becomes a big problem. Whatever in the case of robot or the case of security system, speed becomes more and more important. With paralleling the algorithms for stereo vision, we can get 2 3 times even 20 times speed up. 2 Stereo vision 2.1 Concept of Stereo vision Stereo vision (Stereopsis) is the process in visual perception leading to the sensation of depth from the two slightly different projections of the world onto the retinas of the two eyes. [1]
3 2.2 Human Stereo vision Human has two eyes and one head, each eye can capture one image in a really short time. And the eyes send this two images to out brain. After the computation in the brain, the brain will show us what we saw. There is one way to confirm the images captured by eyes are different: close left eye to capture the image from the right eye, then close the right eye to capture the image from left eye. According to the contradistinction, there are some slightly differences between two images. By the result of the contradistinction, human knows that the brain is not just only mix two images together, but mix them by some methods. Human are able to deduce depth information from differences of a scene as seen by left and right eye. For example, if object one is moving on object two, object two is seen by human but some parts of object is not seen by human (if object two is bigger then object one). Then human know that: object one is closer. 2.3 Stereo vision in computer vision Stereo vision in computer vision is almost the same as stereo vision in human. Stereo vision in computer vision and stereo vision in human both work on the same principle. We can set up two camera as people's eyes, one computer as people's brain. Each camera can capture one image and send them to the brain, which is the computer. Then the computer need some methods to mix the images together. Then the result will present on the screen. 2.4 Contradistinction between human stereo vision and computer stereo vision Human stereo vision and computer stereo vision is almost the same. That's why stereo vision can be presented by computer. But they are not totally the same. Because the computer do not know what people 's brain do. So it is necessary to tell the computer, which methods human used. 3 Parallel in stereo vision Nowadays, stereo vision is not only use in mixing two images together but also used in many areas. For example, we use stereo vision on a robot, to simulate what human can see by their eyes. With this vision, robot can do some tasks for human. Such as pick up one object in the labyrinth, clean the inside of the pipe in some dangerous places. Speed is very important aspect for stereo vision process in real time. It is necessary to parallel it. 3.1 History There are two ways to speed up the real time stereo vision, the first way is use some hardware to speed up. The other way is to parallel the algorithms for stereo vision Hardware There are some existing hardware architectures in the world. One of the hardware architectures is created by J.Falcou, J.serot, T.Chateau and F.Jurie in 2005 [2].
4 Figure 1: Cluster Architecture. The Figure 1 ( from [2] ) shows the cluster architecture. It includes 14 computing nodes. Each node has a dual processor Apple G5 running at 2GHz and 1Gb memory. All nodes connected to a gigabit ethernet switch. And the video streams is provided by two cameras via the FIREWIRE IEEE1394 NETWORK. It has a maximum speed at 400Mb per second. The cluster is doing the job what people's brain do. The camera can capture images and provide the video streams enough for the processing. After each node received the images, they can work on the image, get the result and then send back to the master node. The result will present to the user on the output drive such as screen or printer. But there is a synchronization problem: each node must be work on same frame in the video stream. On the other word, it must wait until each node finished the task on the current frame. In OpenMPI library we can use MPI_Barrier to make sure all the nodes received the images and work on the right images. Here's the result of the cluster Architecture: Figure 2: Result of Cluster Architecture. From the result of the cluster Architecture (Figure2 form [2]), if the task process by using single processor. It will take 992.2ms. With 2 nodes it return the result 479.2ms. And it get the 38.2ms when using 28 nodes. That means it almost got 30 times speed up. A normal video got 30fps, and with the 28 nodes on processing the task, it almost got the quality of the real time video.
5 3.1.2 Software Paralleling in programming takes a very important part in stereo vision. Here are some of the example codes which are working on the Cluster Architecture. Figure 3: Software Architecture,A simple binary thresholding application using in cluster architecture[2] According to the Figure.3 [2], the software architecture contains a data structure for the input and output. The example code received the frame from the cameras via FIREWIRE Network, create a task on the cluster world then process the task on the cluster. After the node finish processing the data, the nodes will send back the data to the root which means the master, and the master will output the data.
6 4 Parallel algorithms for stereo vision Parallel algorithms for stereo vision is based on the stereo vision algorithms. It does the same thing what stereo vision algorithms do. Only different is we will separate the whole task into some small independence task in the master processor, send those small tasks to each slave node and process in the node, get the result back from the slave node, then join them together. Build up the hardware is quite expensive, so parallel the algorithms is a good way to speed up. 4.1 Analysis There are four steps to get the stereo vision in computer vision: Set up the environment, Calibrate on the camera, finding correspondence and compute depth Environment To get the stereo vision, it's necessary to have two cameras and one computer. There are some variables in the stereo vision. Distance of two cameras, the angel from the cameras to the object and any variables related to the cameras and object Calibrate on the camera Nothing is perfect in the world. Same as the cameras. Because of the mirror in the camera are not the same, in some case, a beeline in the real world will present as the curve in the image. In this situation, it is necessary to calibrate the cameras. From the result of calibrating the cameras, they should present the same beeline in two images Finding correspondence The correspondence problem means how to conjugate points in the 3 d in two images. One point in the image captured by left camera may be anywhere in the image captured by right camera. It can be paralleled. Because the point which is the pixel from left camera is not depend on any pixel in the left camera Compute depth We can know how close is the object because our brain can compute depth of the image. The part is related to the computation by triangulation[3].
7 4.2 Methodology Compute depth (Triangulation) The methodology used for compute depth is show as below. Figure 4: Compute depth [3] From the Figure4 [3], all the variables are known when build up the environment. We can get depth by using the formula in the Figure Camera Calibration The common method to calibrate a camera is to take a image of a chessboard. First to do is Canny edge detection, after the detection, fitting the straight line to detect linked edges, then intersecting the lines to obtain the image corners, match image corners and 3 D target chessboard corners which visible in image. Then we can get the pairs of match point. 4.3 Implementation From the section.3 in this report. It tells us all the works are almost independent. Each task is not related to another task. It is possible to do that in parallel. For example, in finding correspondence, the master processor first get a pair of images, broadcast the left image to the slave node. Then separate the right image into pieces. Send those pieces to the slave nodes. The task of each slave node is to find out the pixels in the left image which match their own data (pixels).
8 5 Conclusion This paper show that the architecture of the cluster for real time stereo vision, the concept and algorithms for the stereo vision. In the result of the research, we know that it is possible to implement parallel in stereo vision and obvious that there is speed up. Real time stereo vision problems can be solved by parallel algorithms for stereo vision.
9 References [1] Retrieved 15 MAY Stereopsis, in Wikipedia,The free Encyclopedia, From [2] J. Falcou, J. Serot, T. Chateau, F. Jurie, A Parallel Implementation of a 3D Reconstruction Algorithm for Real Time Vision. in Parallel Computing 2005,2005 [3] Klaus D.Toennies., 5.Stereo Vision (Introduction), in 3D Computer Vision, University Magdeburg [4] R.Hartley and A. Zisserman, Multiple View Geometry, in Computer Vision,Cambridge University Press, 2000, pp [5] O. Faugeras, Three Dimensional Computer Vision: A Geometric Approach, MIT Press,1996, pp [6] R. Y. Tsai, A Versatile Camera Calibration Technique for 3D Machine Vision, IEEE J. Robotics & Automation, RA 3, No. 4, August 1987, pp
Geometry of Multiple views
1 Geometry of Multiple views CS 554 Computer Vision Pinar Duygulu Bilkent University 2 Multiple views Despite the wealth of information contained in a a photograph, the depth of a scene point along the
More informationComplex Sensors: Cameras, Visual Sensing. The Robotics Primer (Ch. 9) ECE 497: Introduction to Mobile Robotics -Visual Sensors
Complex Sensors: Cameras, Visual Sensing The Robotics Primer (Ch. 9) Bring your laptop and robot everyday DO NOT unplug the network cables from the desktop computers or the walls Tuesday s Quiz is on Visual
More informationPractice Exam Sample Solutions
CS 675 Computer Vision Instructor: Marc Pomplun Practice Exam Sample Solutions Note that in the actual exam, no calculators, no books, and no notes allowed. Question 1: out of points Question 2: out of
More informationMachine vision. Summary # 11: Stereo vision and epipolar geometry. u l = λx. v l = λy
1 Machine vision Summary # 11: Stereo vision and epipolar geometry STEREO VISION The goal of stereo vision is to use two cameras to capture 3D scenes. There are two important problems in stereo vision:
More informationComputer Vision Lecture 17
Computer Vision Lecture 17 Epipolar Geometry & Stereo Basics 13.01.2015 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Announcements Seminar in the summer semester
More informationComputer Vision Lecture 17
Announcements Computer Vision Lecture 17 Epipolar Geometry & Stereo Basics Seminar in the summer semester Current Topics in Computer Vision and Machine Learning Block seminar, presentations in 1 st week
More information3D from Images - Assisted Modeling, Photogrammetry. Marco Callieri ISTI-CNR, Pisa, Italy
3D from Images - Assisted Modeling, Photogrammetry Marco Callieri ISTI-CNR, Pisa, Italy 3D from Photos Our not-so-secret dream: obtain a reliable and precise 3D from simple photos Why? Easier, cheaper
More informationAnnouncements. Stereo
Announcements Stereo Homework 2 is due today, 11:59 PM Homework 3 will be assigned today Reading: Chapter 7: Stereopsis CSE 152 Lecture 8 Binocular Stereopsis: Mars Given two images of a scene where relative
More informationTecnologie per la ricostruzione di modelli 3D da immagini. Marco Callieri ISTI-CNR, Pisa, Italy
Tecnologie per la ricostruzione di modelli 3D da immagini Marco Callieri ISTI-CNR, Pisa, Italy 3D from Photos Our not-so-secret dream: obtain a reliable and precise 3D from simple photos Why? Easier, less
More informationBinocular cues to depth PSY 310 Greg Francis. Lecture 21. Depth perception
Binocular cues to depth PSY 310 Greg Francis Lecture 21 How to find the hidden word. Depth perception You can see depth in static images with just one eye (monocular) Pictorial cues However, motion and
More informationLecture 14: Computer Vision
CS/b: Artificial Intelligence II Prof. Olga Veksler Lecture : Computer Vision D shape from Images Stereo Reconstruction Many Slides are from Steve Seitz (UW), S. Narasimhan Outline Cues for D shape perception
More informationDRC A Multi-Camera System on PC-Cluster for Real-time 3-D Tracking. Viboon Sangveraphunsiri*, Kritsana Uttamang, and Pongsakon Pedpunsri
The 23 rd Conference of the Mechanical Engineering Network of Thailand November 4 7, 2009, Chiang Mai A Multi-Camera System on PC-Cluster for Real-time 3-D Tracking Viboon Sangveraphunsiri*, Kritsana Uttamang,
More informationRecap: Features and filters. Recap: Grouping & fitting. Now: Multiple views 10/29/2008. Epipolar geometry & stereo vision. Why multiple views?
Recap: Features and filters Epipolar geometry & stereo vision Tuesday, Oct 21 Kristen Grauman UT-Austin Transforming and describing images; textures, colors, edges Recap: Grouping & fitting Now: Multiple
More informationDISTANCE MEASUREMENT USING STEREO VISION
DISTANCE MEASUREMENT USING STEREO VISION Sheetal Nagar 1, Jitendra Verma 2 1 Department of Electronics and Communication Engineering, IIMT, Greater Noida (India) 2 Department of computer science Engineering,
More informationTecnologie per la ricostruzione di modelli 3D da immagini. Marco Callieri ISTI-CNR, Pisa, Italy
Tecnologie per la ricostruzione di modelli 3D da immagini Marco Callieri ISTI-CNR, Pisa, Italy Who am I? Marco Callieri PhD in computer science Always had the like for 3D graphics... Researcher at the
More informationAnnouncements. Hough Transform [ Patented 1962 ] Generalized Hough Transform, line fitting. Assignment 2: Due today Midterm: Thursday, May 5 in class
Announcements Generalized Hough Transform, line fitting Assignment 2: Due today Midterm: Thursday, May 5 in class Introduction to Computer Vision CSE 152 Lecture 11a What is region like if: 1. λ 1 = 0?
More information7. The Geometry of Multi Views. Computer Engineering, i Sejong University. Dongil Han
Computer Vision 7. The Geometry of Multi Views Computer Engineering, i Sejong University i Dongil Han THE GEOMETRY OF MULTIPLE VIEWS Epipolar Geometry The Stereopsis Problem: Fusion and Reconstruction
More informationAnnouncements. Stereo
Announcements Stereo Homework 1 is due today, 11:59 PM Homework 2 will be assigned on Thursday Reading: Chapter 7: Stereopsis CSE 252A Lecture 8 Binocular Stereopsis: Mars Given two images of a scene where
More informationProject 2 due today Project 3 out today. Readings Szeliski, Chapter 10 (through 10.5)
Announcements Stereo Project 2 due today Project 3 out today Single image stereogram, by Niklas Een Readings Szeliski, Chapter 10 (through 10.5) Public Library, Stereoscopic Looking Room, Chicago, by Phillips,
More informationMultiple View Geometry
Multiple View Geometry Martin Quinn with a lot of slides stolen from Steve Seitz and Jianbo Shi 15-463: Computational Photography Alexei Efros, CMU, Fall 2007 Our Goal The Plenoptic Function P(θ,φ,λ,t,V
More informationCorrespondence and Stereopsis. Original notes by W. Correa. Figures from [Forsyth & Ponce] and [Trucco & Verri]
Correspondence and Stereopsis Original notes by W. Correa. Figures from [Forsyth & Ponce] and [Trucco & Verri] Introduction Disparity: Informally: difference between two pictures Allows us to gain a strong
More informationResearch on an Adaptive Terrain Reconstruction of Sequence Images in Deep Space Exploration
, pp.33-41 http://dx.doi.org/10.14257/astl.2014.52.07 Research on an Adaptive Terrain Reconstruction of Sequence Images in Deep Space Exploration Wang Wei, Zhao Wenbin, Zhao Zhengxu School of Information
More informationThere we are; that's got the 3D screen and mouse sorted out.
Introduction to 3D To all intents and purposes, the world we live in is three dimensional. Therefore, if we want to construct a realistic computer model of it, the model should be three dimensional as
More informationDepth. Common Classification Tasks. Example: AlexNet. Another Example: Inception. Another Example: Inception. Depth
Common Classification Tasks Recognition of individual objects/faces Analyze object-specific features (e.g., key points) Train with images from different viewing angles Recognition of object classes Analyze
More informationHierarchical Matching Techiques for Automatic Image Mosaicing
Hierarchical Matching Techiques for Automatic Image Mosaicing C.L Begg, R Mukundan Department of Computer Science, University of Canterbury, Christchurch, New Zealand clb56@student.canterbury.ac.nz, mukund@cosc.canterbury.ac.nz
More informationMiniature faking. In close-up photo, the depth of field is limited.
Miniature faking In close-up photo, the depth of field is limited. http://en.wikipedia.org/wiki/file:jodhpur_tilt_shift.jpg Miniature faking Miniature faking http://en.wikipedia.org/wiki/file:oregon_state_beavers_tilt-shift_miniature_greg_keene.jpg
More informationCorrecting Radial Distortion of Cameras With Wide Angle Lens Using Point Correspondences
Correcting Radial istortion of Cameras With Wide Angle Lens Using Point Correspondences Leonardo Romero and Cuauhtemoc Gomez Universidad Michoacana de San Nicolas de Hidalgo Morelia, Mich., 58000, Mexico
More informationAn Image-Based Three-Dimensional Digitizer for Pre-Decorating Thermoformed Parts
An Image-Based Three-Dimensional Digitizer for Pre-Decorating Thermoformed Parts J.P. Mellor Rose-Hulman Institute of Technology jpmellor@rose-hulman.edu Abstract Thermoformed plastic parts are pervasive
More informationDoes the Brain do Inverse Graphics?
Does the Brain do Inverse Graphics? Geoffrey Hinton, Alex Krizhevsky, Navdeep Jaitly, Tijmen Tieleman & Yichuan Tang Department of Computer Science University of Toronto How to learn many layers of features
More informationWhy study Computer Vision?
Computer Vision Why study Computer Vision? Images and movies are everywhere Fast-growing collection of useful applications building representations of the 3D world from pictures automated surveillance
More informationFundamentals of Stereo Vision Michael Bleyer LVA Stereo Vision
Fundamentals of Stereo Vision Michael Bleyer LVA Stereo Vision What Happened Last Time? Human 3D perception (3D cinema) Computational stereo Intuitive explanation of what is meant by disparity Stereo matching
More informationIntroduction to 3D Machine Vision
Introduction to 3D Machine Vision 1 Many methods for 3D machine vision Use Triangulation (Geometry) to Determine the Depth of an Object By Different Methods: Single Line Laser Scan Stereo Triangulation
More informationVisual Pathways to the Brain
Visual Pathways to the Brain 1 Left half of visual field which is imaged on the right half of each retina is transmitted to right half of brain. Vice versa for right half of visual field. From each eye
More informationRecap from Previous Lecture
Recap from Previous Lecture Tone Mapping Preserve local contrast or detail at the expense of large scale contrast. Changing the brightness within objects or surfaces unequally leads to halos. We are now
More informationDoes the Brain do Inverse Graphics?
Does the Brain do Inverse Graphics? Geoffrey Hinton, Alex Krizhevsky, Navdeep Jaitly, Tijmen Tieleman & Yichuan Tang Department of Computer Science University of Toronto The representation used by the
More informationStereo 3D camera supports automated storage of packaging Out of the box
Stereo 3D camera supports automated storage of packaging Out of the box The automation of pick and place processes is one of the things that 3D machine vision does best. After all, fast and reliable identification
More informationPassive 3D Photography
SIGGRAPH 2000 Course on 3D Photography Passive 3D Photography Steve Seitz Carnegie Mellon University University of Washington http://www.cs cs.cmu.edu/~ /~seitz Visual Cues Shading Merle Norman Cosmetics,
More informationRange Sensors (time of flight) (1)
Range Sensors (time of flight) (1) Large range distance measurement -> called range sensors Range information: key element for localization and environment modeling Ultrasonic sensors, infra-red sensors
More informationA COMPREHENSIVE SIMULATION SOFTWARE FOR TEACHING CAMERA CALIBRATION
XIX IMEKO World Congress Fundamental and Applied Metrology September 6 11, 2009, Lisbon, Portugal A COMPREHENSIVE SIMULATION SOFTWARE FOR TEACHING CAMERA CALIBRATION David Samper 1, Jorge Santolaria 1,
More informationImage Based Reconstruction II
Image Based Reconstruction II Qixing Huang Feb. 2 th 2017 Slide Credit: Yasutaka Furukawa Image-Based Geometry Reconstruction Pipeline Last Lecture: Multi-View SFM Multi-View SFM This Lecture: Multi-View
More informationTHE FOURTH SPATIAL DIMENSION
THE FOURTH SPATIAL DIMENSION Have you seen a film, where the actor is sitting on a couch, the camera is behind him, and he puts a cigarette to his lips, puffs, expels the smoke, then the camera focuses
More informationProcessing Framework Proposed by Marr. Image
Processing Framework Proposed by Marr Recognition 3D structure; motion characteristics; surface properties Shape From stereo Motion flow Shape From motion Color estimation Shape From contour Shape From
More information3D Sensing. 3D Shape from X. Perspective Geometry. Camera Model. Camera Calibration. General Stereo Triangulation.
3D Sensing 3D Shape from X Perspective Geometry Camera Model Camera Calibration General Stereo Triangulation 3D Reconstruction 3D Shape from X shading silhouette texture stereo light striping motion mainly
More informationMulti-Robot Navigation and Coordination
Multi-Robot Navigation and Coordination Daniel Casner and Ben Willard Kurt Krebsbach, Advisor Department of Computer Science, Lawrence University, Appleton, Wisconsin 54912 daniel.t.casner@ieee.org, benjamin.h.willard@lawrence.edu
More information(Refer Slide Time 00:17) Welcome to the course on Digital Image Processing. (Refer Slide Time 00:22)
Digital Image Processing Prof. P. K. Biswas Department of Electronics and Electrical Communications Engineering Indian Institute of Technology, Kharagpur Module Number 01 Lecture Number 02 Application
More informationAssignment 2: Stereo and 3D Reconstruction from Disparity
CS 6320, 3D Computer Vision Spring 2013, Prof. Guido Gerig Assignment 2: Stereo and 3D Reconstruction from Disparity Out: Mon Feb-11-2013 Due: Mon Feb-25-2013, midnight (theoretical and practical parts,
More informationNeural Nets. CSCI 5582, Fall 2007
Neural Nets CSCI 5582, Fall 2007 Assignments For this week: Chapter 20, section 5 Problem Set 3 is due a week from today Neural Networks: Some First Concepts Each neural element is loosely based on the
More information12/3/2009. What is Computer Vision? Applications. Application: Assisted driving Pedestrian and car detection. Application: Improving online search
Introduction to Artificial Intelligence V22.0472-001 Fall 2009 Lecture 26: Computer Vision Rob Fergus Dept of Computer Science, Courant Institute, NYU Slides from Andrew Zisserman What is Computer Vision?
More information10/5/09 1. d = 2. Range Sensors (time of flight) (2) Ultrasonic Sensor (time of flight, sound) (1) Ultrasonic Sensor (time of flight, sound) (2) 4.1.
Range Sensors (time of flight) (1) Range Sensors (time of flight) (2) arge range distance measurement -> called range sensors Range information: key element for localization and environment modeling Ultrasonic
More informationAn Algorithm for Seamless Image Stitching and Its Application
An Algorithm for Seamless Image Stitching and Its Application Jing Xing, Zhenjiang Miao, and Jing Chen Institute of Information Science, Beijing JiaoTong University, Beijing 100044, P.R. China Abstract.
More informationComputer Vision. Introduction
Computer Vision Introduction Filippo Bergamasco (filippo.bergamasco@unive.it) http://www.dais.unive.it/~bergamasco DAIS, Ca Foscari University of Venice Academic year 2016/2017 About this course Official
More informationCOMP 102: Computers and Computing
COMP 102: Computers and Computing Lecture 23: Computer Vision Instructor: Kaleem Siddiqi (siddiqi@cim.mcgill.ca) Class web page: www.cim.mcgill.ca/~siddiqi/102.html What is computer vision? Broadly speaking,
More informationCPSC 425: Computer Vision
1 / 45 CPSC 425: Computer Vision Instructor: Fred Tung ftung@cs.ubc.ca Department of Computer Science University of British Columbia Lecture Notes 2015/2016 Term 2 2 / 45 Menu March 3, 2016 Topics: Hough
More informationStereoscopic Systems Part 1
Stereoscopic Systems Part 1 Terminology: Stereoscopic vs. 3D 3D Animation refers to computer animation created with programs (like Maya) that manipulate objects in a 3D space, though the rendered image
More informationStereo Vision. MAN-522 Computer Vision
Stereo Vision MAN-522 Computer Vision What is the goal of stereo vision? The recovery of the 3D structure of a scene using two or more images of the 3D scene, each acquired from a different viewpoint in
More informationAdaptive Zoom Distance Measuring System of Camera Based on the Ranging of Binocular Vision
Adaptive Zoom Distance Measuring System of Camera Based on the Ranging of Binocular Vision Zhiyan Zhang 1, Wei Qian 1, Lei Pan 1 & Yanjun Li 1 1 University of Shanghai for Science and Technology, China
More informationProject 4 Results. Representation. Data. Learning. Zachary, Hung-I, Paul, Emanuel. SIFT and HoG are popular and successful.
Project 4 Results Representation SIFT and HoG are popular and successful. Data Hugely varying results from hard mining. Learning Non-linear classifier usually better. Zachary, Hung-I, Paul, Emanuel Project
More informationComputer and Machine Vision
Computer and Machine Vision Lecture Week 12 Part-2 Additional 3D Scene Considerations March 29, 2014 Sam Siewert Outline of Week 12 Computer Vision APIs and Languages Alternatives to C++ and OpenCV API
More informationA Vision System for Automatic State Determination of Grid Based Board Games
A Vision System for Automatic State Determination of Grid Based Board Games Michael Bryson Computer Science and Engineering, University of South Carolina, 29208 Abstract. Numerous programs have been written
More informationHIGH SPEED 3-D MEASUREMENT SYSTEM USING INCOHERENT LIGHT SOURCE FOR HUMAN PERFORMANCE ANALYSIS
HIGH SPEED 3-D MEASUREMENT SYSTEM USING INCOHERENT LIGHT SOURCE FOR HUMAN PERFORMANCE ANALYSIS Takeo MIYASAKA, Kazuhiro KURODA, Makoto HIROSE and Kazuo ARAKI School of Computer and Cognitive Sciences,
More informationA High Speed Face Measurement System
A High Speed Face Measurement System Kazuhide HASEGAWA, Kazuyuki HATTORI and Yukio SATO Department of Electrical and Computer Engineering, Nagoya Institute of Technology Gokiso, Showa, Nagoya, Japan, 466-8555
More informationMulti-view stereo. Many slides adapted from S. Seitz
Multi-view stereo Many slides adapted from S. Seitz Beyond two-view stereo The third eye can be used for verification Multiple-baseline stereo Pick a reference image, and slide the corresponding window
More informationLast update: May 4, Vision. CMSC 421: Chapter 24. CMSC 421: Chapter 24 1
Last update: May 4, 200 Vision CMSC 42: Chapter 24 CMSC 42: Chapter 24 Outline Perception generally Image formation Early vision 2D D Object recognition CMSC 42: Chapter 24 2 Perception generally Stimulus
More informationMultiple View Geometry
Multiple View Geometry CS 6320, Spring 2013 Guest Lecture Marcel Prastawa adapted from Pollefeys, Shah, and Zisserman Single view computer vision Projective actions of cameras Camera callibration Photometric
More informationBackpropagation in Neural Nets, and an Introduction to Vision. CSCI 5582, Fall 2007
Backpropagation in Neural Nets, and an Introduction to Vision CSCI 5582, Fall 2007 Assignments Problem Set 3 is due a week from today The Update Rule for a Weighted Edge of a Perceptron To update the weight
More informationTable of Contents. Questions or problems?
1 Introduction Overview Setting Up Occluders Shadows and Occlusion LODs Creating LODs LOD Selection Optimization Basics Controlling the Hierarchy MultiThreading Multiple Active Culling Cameras Umbra Comparison
More informationEnhancing the Depth Discontinuities by Pixel-to-Pixel Algorithm Using MPI
Enhancing the Depth Discontinuities by Pixel-to-Pixel Algorithm Using MPI Thanathip Limna and Pichaya Tandayya Department of Computer Engineering, Faculty of Engineering, Prince of Songkla University,
More informationComputer and Machine Vision
Computer and Machine Vision Lecture Week 4 Part-2 February 5, 2014 Sam Siewert Outline of Week 4 Practical Methods for Dealing with Camera Streams, Frame by Frame and De-coding/Re-encoding for Analysis
More informationCONTENTS. High-Accuracy Stereo Depth Maps Using Structured Light. Yeojin Yoon
[Paper Seminar 7] CVPR2003, Vol.1, pp.195-202 High-Accuracy Stereo Depth Maps Using Structured Light Daniel Scharstein Middlebury College Richard Szeliski Microsoft Research 2012. 05. 30. Yeojin Yoon Introduction
More informationChapter 7. Conclusions and Future Work
Chapter 7 Conclusions and Future Work In this dissertation, we have presented a new way of analyzing a basic building block in computer graphics rendering algorithms the computational interaction between
More informationProject report Augmented reality with ARToolKit
Project report Augmented reality with ARToolKit FMA175 Image Analysis, Project Mathematical Sciences, Lund Institute of Technology Supervisor: Petter Strandmark Fredrik Larsson (dt07fl2@student.lth.se)
More informationThink-Pair-Share. What visual or physiological cues help us to perceive 3D shape and depth?
Think-Pair-Share What visual or physiological cues help us to perceive 3D shape and depth? [Figure from Prados & Faugeras 2006] Shading Focus/defocus Images from same point of view, different camera parameters
More informationNew Sony DepthSense TM ToF Technology
ADVANCED MATERIAL HANDLING WITH New Sony DepthSense TM ToF Technology Jenson Chang Product Marketing November 7, 2018 1 3D SENSING APPLICATIONS Pick and Place Drones Collision Detection People Counting
More informationToday. Stereo (two view) reconstruction. Multiview geometry. Today. Multiview geometry. Computational Photography
Computational Photography Matthias Zwicker University of Bern Fall 2009 Today From 2D to 3D using multiple views Introduction Geometry of two views Stereo matching Other applications Multiview geometry
More information3D Sensing and Reconstruction Readings: Ch 12: , Ch 13: ,
3D Sensing and Reconstruction Readings: Ch 12: 12.5-6, Ch 13: 13.1-3, 13.9.4 Perspective Geometry Camera Model Stereo Triangulation 3D Reconstruction by Space Carving 3D Shape from X means getting 3D coordinates
More informationStereo. 11/02/2012 CS129, Brown James Hays. Slides by Kristen Grauman
Stereo 11/02/2012 CS129, Brown James Hays Slides by Kristen Grauman Multiple views Multi-view geometry, matching, invariant features, stereo vision Lowe Hartley and Zisserman Why multiple views? Structure
More informationRecognition of Object Contours from Stereo Images: an Edge Combination Approach
Recognition of Object Contours from Stereo Images: an Edge Combination Approach Margrit Gelautz and Danijela Markovic Institute for Software Technology and Interactive Systems, Vienna University of Technology
More informationProjector Calibration for Pattern Projection Systems
Projector Calibration for Pattern Projection Systems I. Din *1, H. Anwar 2, I. Syed 1, H. Zafar 3, L. Hasan 3 1 Department of Electronics Engineering, Incheon National University, Incheon, South Korea.
More informationLecture 9: Epipolar Geometry
Lecture 9: Epipolar Geometry Professor Fei Fei Li Stanford Vision Lab 1 What we will learn today? Why is stereo useful? Epipolar constraints Essential and fundamental matrix Estimating F (Problem Set 2
More informationPerception and Action using Multilinear Forms
Perception and Action using Multilinear Forms Anders Heyden, Gunnar Sparr, Kalle Åström Dept of Mathematics, Lund University Box 118, S-221 00 Lund, Sweden email: {heyden,gunnar,kalle}@maths.lth.se Abstract
More informationIMPACT OF SUBPIXEL PARADIGM ON DETERMINATION OF 3D POSITION FROM 2D IMAGE PAIR Lukas Sroba, Rudolf Ravas
162 International Journal "Information Content and Processing", Volume 1, Number 2, 2014 IMPACT OF SUBPIXEL PARADIGM ON DETERMINATION OF 3D POSITION FROM 2D IMAGE PAIR Lukas Sroba, Rudolf Ravas Abstract:
More informationStereo Observation Models
Stereo Observation Models Gabe Sibley June 16, 2003 Abstract This technical report describes general stereo vision triangulation and linearized error modeling. 0.1 Standard Model Equations If the relative
More informationPassive 3D Photography
SIGGRAPH 99 Course on 3D Photography Passive 3D Photography Steve Seitz Carnegie Mellon University http:// ://www.cs.cmu.edu/~seitz Talk Outline. Visual Cues 2. Classical Vision Algorithms 3. State of
More informationUniversity of Cambridge Engineering Part IIB Module 4F12: Computer Vision and Robotics Handout 1: Introduction
University of Cambridge Engineering Part IIB Module 4F12: Computer Vision and Robotics Handout 1: Introduction Roberto Cipolla October 2006 Introduction 1 What is computer vision? Vision is about discovering
More information1 Projective Geometry
CIS8, Machine Perception Review Problem - SPRING 26 Instructions. All coordinate systems are right handed. Projective Geometry Figure : Facade rectification. I took an image of a rectangular object, and
More informationA Survey of Light Source Detection Methods
A Survey of Light Source Detection Methods Nathan Funk University of Alberta Mini-Project for CMPUT 603 November 30, 2003 Abstract This paper provides an overview of the most prominent techniques for light
More informationDigital 3D technologies
Digital 3D technologies A simple introduction Marco Callieri ISTI-CNR callieri@isti.cnr.it Who Am I? Marco Callieri Master Degree & PhD in computer science Researcher at the Visual Computing Lab, ISTI-CNR,
More informationDynamic Reconstruction for Coded Aperture Imaging Draft Unpublished work please do not cite or distribute.
Dynamic Reconstruction for Coded Aperture Imaging Draft 1.0.1 Berthold K.P. Horn 2007 September 30. Unpublished work please do not cite or distribute. The dynamic reconstruction technique makes it possible
More informationC / 35. C18 Computer Vision. David Murray. dwm/courses/4cv.
C18 2015 1 / 35 C18 Computer Vision David Murray david.murray@eng.ox.ac.uk www.robots.ox.ac.uk/ dwm/courses/4cv Michaelmas 2015 C18 2015 2 / 35 Computer Vision: This time... 1. Introduction; imaging geometry;
More informationStructured light 3D reconstruction
Structured light 3D reconstruction Reconstruction pipeline and industrial applications rodola@dsi.unive.it 11/05/2010 3D Reconstruction 3D reconstruction is the process of capturing the shape and appearance
More informationFeature Transfer and Matching in Disparate Stereo Views through the use of Plane Homographies
Feature Transfer and Matching in Disparate Stereo Views through the use of Plane Homographies M. Lourakis, S. Tzurbakis, A. Argyros, S. Orphanoudakis Computer Vision and Robotics Lab (CVRL) Institute of
More informationWhy study Computer Vision?
Why study Computer Vision? Images and movies are everywhere Fast-growing collection of useful applications building representations of the 3D world from pictures automated surveillance (who s doing what)
More informationDense 3-D Reconstruction of an Outdoor Scene by Hundreds-baseline Stereo Using a Hand-held Video Camera
Dense 3-D Reconstruction of an Outdoor Scene by Hundreds-baseline Stereo Using a Hand-held Video Camera Tomokazu Satoy, Masayuki Kanbaray, Naokazu Yokoyay and Haruo Takemuraz ygraduate School of Information
More informationEpipolar Geometry Prof. D. Stricker. With slides from A. Zisserman, S. Lazebnik, Seitz
Epipolar Geometry Prof. D. Stricker With slides from A. Zisserman, S. Lazebnik, Seitz 1 Outline 1. Short introduction: points and lines 2. Two views geometry: Epipolar geometry Relation point/line in two
More informationAccurate 3D Face and Body Modeling from a Single Fixed Kinect
Accurate 3D Face and Body Modeling from a Single Fixed Kinect Ruizhe Wang*, Matthias Hernandez*, Jongmoo Choi, Gérard Medioni Computer Vision Lab, IRIS University of Southern California Abstract In this
More informationAdobe Photoshop How to Use the Marquee Selection Tools
Adobe Photoshop How to Use the Marquee Selection Tools In Photoshop there are various ways to make a selection and also various reasons why you'd want to make a selection. You may want to remove something
More informationA New Algorithm for Shape Detection
IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 19, Issue 3, Ver. I (May.-June. 2017), PP 71-76 www.iosrjournals.org A New Algorithm for Shape Detection Hewa
More informationL2 Data Acquisition. Mechanical measurement (CMM) Structured light Range images Shape from shading Other methods
L2 Data Acquisition Mechanical measurement (CMM) Structured light Range images Shape from shading Other methods 1 Coordinate Measurement Machine Touch based Slow Sparse Data Complex planning Accurate 2
More informationImaging Partnership STEMM PRACTITIONER RESOURCES
Imaging Partnership STEMM PRACTITIONER RESOURCES The Eye Vs. The Camera LESSON FOUR What you will learn: The differences and similarities between how our eyes and a camera captures an image. Understanding
More information3D Modeling of Objects Using Laser Scanning
1 3D Modeling of Objects Using Laser Scanning D. Jaya Deepu, LPU University, Punjab, India Email: Jaideepudadi@gmail.com Abstract: In the last few decades, constructing accurate three-dimensional models
More information